procyberian/gcc
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Match: Support form 2 for the .SAT_TRUNC

Browse source 
This patch would like to add form 2 support for the .SAT_TRUNC.  Aka:

Form 2:
  #define DEF_SAT_U_TRUC_FMT_2(NT, WT)     \
  NT __attribute__((noinline))             \
  sat_u_truc_##WT##_to_##NT##_fmt_2 (WT x) \
  {                                        \
    bool overflow = x > (WT)(NT)(-1);      \
    return overflow ? (NT)-1 : (NT)x;      \
  }

DEF_SAT_U_TRUC_FMT_2(uint32, uint64)

Before this patch:
   3   │
   4   │ __attribute__((noinline))
   5   │ uint32_t sat_u_truc_uint64_t_to_uint32_t_fmt_2 (uint64_t x)
   6   │ {
   7   │   uint32_t _1;
   8   │   long unsigned int _3;
   9   │
  10   │ ;;   basic block 2, loop depth 0
  11   │ ;;    pred:       ENTRY
  12   │   _3 = MIN_EXPR <x_2(D), 4294967295>;
  13   │   _1 = (uint32_t) _3;
  14   │   return _1;
  15   │ ;;    succ:       EXIT
  16   │
  17   │ }

After this patch:
   3   │
   4   │ __attribute__((noinline))
   5   │ uint32_t sat_u_truc_uint64_t_to_uint32_t_fmt_2 (uint64_t x)
   6   │ {
   7   │   uint32_t _1;
   8   │
   9   │ ;;   basic block 2, loop depth 0
  10   │ ;;    pred:       ENTRY
  11   │   _1 = .SAT_TRUNC (x_2(D)); [tail call]
  12   │   return _1;
  13   │ ;;    succ:       EXIT
  14   │
  15   │ }

The below test suites are passed for this patch:
1. The x86 bootstrap test.
2. The x86 fully regression test.
3. The rv64gcv fully regresssion test.

gcc/ChangeLog:

	* match.pd: Add form 2 for .SAT_TRUNC.
	* tree-ssa-math-opts.cc (math_opts_dom_walker::after_dom_children):
	Add new case NOP_EXPR,  and try to match SAT_TRUNC.

Signed-off-by: Pan Li <pan2.li@intel.com>
This commit is contained in:
Pan Li 2024-07-05 20:36:35 +08:00
parent 1ae5fc24e8
commit 80e446e829
2 changed files with 20 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

17
gcc/match.pd
View file

@ -3234,7 +3234,7 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
(if (INTEGRAL_TYPE_P (type) && TYPE_UNSIGNED (type)
&& types_match (type, @0, @1))))
/* Unsigned saturation truncate, case 1 (), sizeof (WT) > sizeof (NT).
/* Unsigned saturation truncate, case 1, sizeof (WT) > sizeof (NT).
SAT_U_TRUNC = (NT)x | (NT)(-(X > (WT)(NT)(-1))). */
(match (unsigned_integer_sat_trunc @0)
(bit_ior:c (negate (convert (gt @0 INTEGER_CST@1)))
@ -3250,6 +3250,21 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
}
(if (otype_precision < itype_precision && wi::eq_p (trunc_max, int_cst))))))
/* Unsigned saturation truncate, case 2, sizeof (WT) > sizeof (NT).
SAT_U_TRUNC = (NT)(MIN_EXPR (X, 255)). */
(match (unsigned_integer_sat_trunc @0)
(convert (min @0 INTEGER_CST@1))
(if (INTEGRAL_TYPE_P (type) && TYPE_UNSIGNED (type)
&& TYPE_UNSIGNED (TREE_TYPE (@0)))
(with
{
unsigned itype_precision = TYPE_PRECISION (TREE_TYPE (@0));
unsigned otype_precision = TYPE_PRECISION (type);
wide_int trunc_max = wi::mask (otype_precision, false, itype_precision);
wide_int int_cst = wi::to_wide (@1, itype_precision);
}
(if (otype_precision < itype_precision && wi::eq_p (trunc_max, int_cst))))))
/* x > y && x != XXX_MIN --> x > y
x > y && x == XXX_MIN --> false . */
(for eqne (eq ne)

4
gcc/tree-ssa-math-opts.cc
View file

@ -6170,6 +6170,10 @@ math_opts_dom_walker::after_dom_children (basic_block bb)
match_unsigned_saturation_sub (&gsi, as_a<gassign *> (stmt));
break;
case NOP_EXPR:
match_unsigned_saturation_trunc (&gsi, as_a<gassign *> (stmt));
break;
default:;
}
}